mcp-gittree
FastMCP server for managing multi-project git bare repositories and worktrees using gix. Provides tools for session, project, and workspace management, enabling creation, listing, fetching, and checkout operations without the git CLI.
README
mcp-gittree
Simple FastMCP server for multi-project git bare + worktrees (Rust gix, no git CLI).
| Layer | Meaning | Path |
|---|---|---|
| project | git repo | {type.root}/{project}/.bare |
| workspace | physical checkout (session current) | {type.root}/{project}/{workspace}/ |
| worktree | linked git worktree | same path |
Quick start
# install
uv sync --all-packages
cd packages/mcp-gittree-git && uv run maturin develop && cd ../..
# config: see examples/gittree.toml ([types.*] roots + [[project]])
uv run mcp-gittree --config examples/gittree.toml
Env alternative: MCP_GITTREE_CONFIG=/path/to/gittree.toml.
Tools
Session: create_session, list_sessions, get_session, set_current_workspace
Projects: list_project, add_project(name, git_url, type), check_fetch_project(name), fetch_all_projects
Workspaces: list_workspace, new_workspace, create_worktree (new branch), checkout_worktree, prune_workspace (metadata for deleted=true only)
Not provided: rm/delete, commit, push, git CLI.
Config
[types.work]
root = "~/work"
[types.pet]
root = "~/pet"
[[project]]
name = "my-app"
type = "work"
origin = "https://github.com/org/my-app.git"
type is required; roots come from [types.<name>]. Registry writes are serialized (lock + atomic rename).
Prompt / skill
- MCP prompt
gittree_workflow— short checklist for agents - Agent skill:
skills/gittree-workflow/SKILL.md
Flow: session → add/list project → workspace → set current → work only there → fetch / prune.
Tests / coverage
make test-rust
make test
make cov-py # median ≥ 93%
make cov-rust # median ≥ 93%
make e2e-vmcp # FastMCP Client tools/call (vmcp-style)
scripts/e2e_vmcp.py default mode uses Client(mcp) (real MCP tool calls).
Against a remote vmcp / HTTP MCP gateway:
MCP_GITTREE_MCP_URL=https://…/mcp \
MCP_GITTREE_E2E_GIT_URL=https://github.com/org/repo.git \
uv run python scripts/e2e_vmcp.py
Report: /opt/cursor/artifacts/e2e-vmcp-report.json (or MCP_GITTREE_E2E_REPORT).
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.